fix(gemini): usage metadata

[QIN2DIM]

Related Issues or Context

Related: #1360

This PR introduces a solution to fully resolve token counting issues for prompt_tokens and completion_tokens in multi-modal QA scenarios using the Gemini GenAI SDK.

---

1. Accurate Token Counting in Multi-Modal QA

• Problem:
  In the Gemini GenAI SDK, token statistics for prompt_tokens and completion_tokens were previously inaccurate in multi-modal QA scenarios, leading to inconsistencies in total token usage reporting.
• Fix:
  Implemented a solution that ensures:
  • total_token_count is always consistent.
  • Correct pricing is applied for the following modalities: IMAGE, VIDEO, TEXT, and DOCUMENT.
• Limitations:
  Due to current constraints in Dify:
  • Different modalities cannot be assigned distinct token prices.
  • The system does not track tiered (step-wise) pricing.
  • As a result, pricing accuracy cannot be guaranteed in the following scenarios:
    • Caching
    • Grounding
    • Audio input
    • LiveAPI
    • Gemini 2.5 Pro with ultra-long context.

completion_tokens = thoughts_token_count + candidates_token_count
prompt_tokens = prompt_tokens_standard
total_tokens= prompt_tokens + completion_tokens + (tool_use_prompts)
tool_use_prompts = 0

This PR contains Changes to Non-Plugin

• Documentation
• Other

This PR contains Changes to Non-LLM Models Plugin

• I have Run Comprehensive Tests Relevant to My Changes

This PR contains Changes to LLM Models Plugin

• My Changes Affect Message Flow Handling (System Messages and User→Assistant Turn-Taking)

• My Changes Affect Tool Interaction Flow (Multi-Round Usage and Output Handling, for both Agent App and Agent Node)

• My Changes Affect Multimodal Input Handling (Images, PDFs, Audio, Video, etc.)

• My Changes Affect Multimodal Output Generation (Images, Audio, Video, etc.)

• My Changes Affect Structured Output Format (JSON, XML, etc.)

• My Changes Affect Token Consumption Metrics

• My Changes Affect Other LLM Functionalities (Reasoning Process, Grounding, Prompt Caching, etc.)

• Other Changes (Add New Models, Fix Model Parameters etc.)

Version Control (Any Changes to the Plugin Will Require Bumping the Version)

• I have Bumped Up the Version in Manifest.yaml (Top-Level Version Field, Not in Meta Section)

Dify Plugin SDK Version

• I have Ensured dify_plugin>=0.3.0,<0.5.0 is in requirements.txt (SDK docs)

Environment Verification (If Any Code Changes)

Local Deployment Environment

• Dify Version is: , I have Tested My Changes on Local Deployment Dify with a Clean Environment That Matches the Production Configuration.

SaaS Environment

• I have Tested My Changes on cloud.dify.ai with a Clean Environment That Matches the Production Configuration